Pesme, Scott
- Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity
2021/06/17 by Scott Pesme, Loucas Pillaud‐Vivien, Pesme, Scott +3 · 6 citations
Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM #Markov Chains and Monte Carlo Methods #Neural Networks and Applications #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques
- Saddle-to-Saddle Dynamics in Diagonal Linear Networks
2023/04/02 by Scott Pesme, Nicolas Flammarion, Pesme, Scott +1 · 5 citations
Computer Science · Mathematics · #FOS: Computer and information sciences #FOS: Mathematics #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Markov Chains and Monte Carlo Methods #Optimization and Control (math.OC) #Stochastic Gradient Optimization Techniques
- (S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability
2023/02/17 by Even, Mathieu, Pesme, Scott, Gunasekar, Suriya +1 · 2 citations
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Online Robust Regression via SGD on the l1 loss
2020/07/01 by Scott Pesme, Pesme, Scott, Nicolas Flammarion +1 · 1 citation
Computer Science · Engineering · Mathematics · #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC) #Sparse and Compressive Sensing Techniques #Statistical Methods and Inference #Stochastic Gradient Optimization Techniques
- A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation
2025/05/26 by Boursier, Etienne, Pesme, Scott, Dragomir, Radu-Alexandru · 2 citations
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks
2024/03/08 by Hristo Papazov, Scott Pesme, Papazov, Hristo +3 · 1 citation
Computer Science · #Neural Networks and Applications
- Implicit Bias of Mirror Flow on Separable Data
2024/06/18 by Pesme, Scott, Dragomir, Radu-Alexandru, Flammarion, Nicolas · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)